Perioperative Hypotension Prediction: Innovation Brief

Idea: How to predict hypotension in the Operating Room and ICUs.

Current state:
Perioperative medicine plays a significant role in healthcare both clinically (e.g., 42 million cases a year in the U.S.) and economically (∼50-60% of total annual budgets of U.S. hospitals)^1,2,3. Despite rapid advancements in data availability and AI-augmented clinical decision-making, current practices in perioperative medicine still suffer from lack of specificity and accuracy at the patient level in order to promote personalized and precision medicine. Preoperatively, American Society of Anesthesiologists (ASA) physical status classification, proactive diagnosis and appropriate patient specific interventions are needed to determine whether the patient will benefit from surgery, when the surgery should be performed, what anesthetic techniques should be used, and which perioperative pathway is the best.⁴ Intraoperatively, studies showed that new onset of cardiopulmonary instability (CPI) is common in patients undergoing surgery and can cause increased morbidity and mortality. Hypotension is one major cause for CPI. Given the current availability of rich intraoperative data, it is imperative to develop AI tools to enable anesthesiologists to identify impending emergencies (e.g., hypotension) 15 minutes before it happens, and to provide anesthesiologists with precise contingency recommendations. Postoperatively, utilizing the preoperative and intraoperative data (e.g., co-morbidities, blood loss, complications, hypotension) to predict post-surgical outcomes (e.g., need for ICU admission, length of hospital stay) is an integral part of the perioperative clinical optimization process and must be considered holistically. In 2020 an urgent call for action⁵ to effectively deploy modern data science and artificial intelligence (AI) in perioperative medicine^5,6,7,8 was issued by the surgery and anesthesiology community.

Innovation:
Hypotension Prediction Index from Edwards LifeSciences could predict hypotension within the next five minutes based on arterial line waveform analysis.

Evidence:
HPI was found to predict hypotensive episodes during noncardiac and cardiac surgeries with a high degree of sensitivity and specificity.⁹

Potential Impact:
The Hypotension Prediction Index provides real time and continuous prediction of impending hypotension before its occurrence and has superior predictive ability than the commonly measured perioperative hemodynamic variables. As the Hypotension Prediction Index increases, so does the actual event rate, and the time to hypotension decreases. Future work is necessary to show if avoiding intraoperative hypotension using the Hypotension Prediction Index can reduce postoperative complications and improve patient outcome.

Average Cost:
$300 per use

Key words:
hypotension, surgery, anesthesia, machine learning.

References:

1.  R. M. Pearse, D. A. Harrison, P. James, D. Watson, C. Hinds, A. Rhodes, R. M. Grounds, and E. D. Bennett, “Identification and characterisation of the high-risk surgical population in the United Kingdom,” Critical care, vol. 10, no. 3, pp. 1–6, 2006.

2.  R. M. Pearse, R. P. Moreno, P. Bauer, P. Pelosi, P. Metnitz, C. Spies, B. Vallet, J.-L. Vincent, A. Hoeft, A. Rhodes et al., “Mortality after surgery in Europe: a 7 day cohort study,” The Lancet, vol. 380, no. 9847, pp. 1059–1065, 2012.

3. K. W. McDermott, W. J. Freeman, and A. Elixhauser, “statistical brief# 233,” Healthcare Cost and Utilization Project (HCUP) Statistical Briefs, pp. Agency–for, 2017.

4.  P. Gambus and S. L. Shafer, “Artificial intelligence for everyone,” Anesthesiology, vol. 128, no. 3, pp. 431–433, 2018.

5.  S. Aronson, G. Martin, P. Gulur, M. E. Lipkin, S. A. Lagoo-Deenadayalan, C. R. Mantyh, D. E. Attarian, J. P. Mathew, and A. D. Kirk, “Preoperative optimization: a continued call to action,” Anesthesia & Analgesia, vol. 130, no. 4, pp. 808–810, 2020.

6.  S. A. Finkler, “The distinction between cost and charges,” Annals of internal medicine, vol. 96, no. 1, pp. 102–109, 1982.

7. M. Grocott and R. Pearse, “Perioperative medicine: the future of anaesthesia?” pp. 723–726, 2012.

8. E. P. Harris, D. B. MacDonald, L. Boland, S. Boet, M. M. Lalu, and D. I. McIsaac, “Personalized perioperative medicine: a scoping review of personalized assessment and communication of risk before surgery,” Canadian Journal of Anesthesia/Journal canadien d’anesthÅLesie, vol. 66, no. 9, pp. 1026–1037, 2019.

9. Davies SJ, Vistisen ST, Jian Z, Hatib F, Scheeren TWL. Ability of an Arterial Waveform Analysis-Derived Hypotension Prediction Index to Predict Future Hypotensive Events in Surgical Patients. Anesth Analg. 2020 Feb;130(2):352-359.